An approximate sampler for energy-based models with divergence diagnostics
Abstract: Energy-based models (EBMs) allow flexible specifications of probability distributions. However, sampling from EBMs is non-trivial, usually requiring approximate techniques such as Markov chain Monte Carlo (MCMC). A major downside of MCMC sampling is that it is often impossible to compute the divergence of the sampling distribution from the target distribution: therefore, the quality of the samples cannot be guaranteed. Here, we introduce quasi-rejection sampling (QRS), a simple extension of rejection sampling that performs approximate sampling, but, crucially, does provide divergence diagnostics (in terms of f-divergences, such as KL divergence and total variation distance). We apply QRS to sampling from discrete EBMs over text for controlled generation. We show that we can sample from such EBMs with arbitrary precision in exchange for sampling efficiency and quantify the trade-off between the two by means of the aforementioned diagnostics.
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: Camera-ready revision.
Assigned Action Editor: ~Michael_U._Gutmann1
Submission Number: 408